检索结果-内蒙古大学图书馆

An improved method of speech recognition based on probabilistic neural network ensembles

学校读者我要写书评

暂无评论

An improved method of speech recognition based on probabilis...

International Conference on Natural Computation (ICNC)

作者： Xinguang Li Shengbin Zhang Sumei Li Junyu Chen GDUFS LAB for Language Engineering and Computing Guangzhou China GDUFS Educational Technology Center Guangzhou China GDUFS CISCO School of Informatics Guangzhou China

ISBN: (纸本)9781467376808

The neural network method is one of the most important methods in the field of speech recognition. In this paper, we propose a new speech recognition method, probabilistic neural network (PNN) ensembles, where the Bagging ensembles method is used to form a speech recognition model with probabilistic neural networks integrated, to implement a speaker-independent English speech recognition system. This paper also demonstrates that before speech recognition, applying segment clustering algorithm to the extracted speech data, i.e., the process of time warping, can ensure the validity of dataset and the performance of PNN. Through experiments, the experimental results show that the PNN ensembles method has faster modeling speed and higher recognition rate than the single BP (Back Propagation) and the BP ensembles method, and has higher recognition rate than the traditional PNN method.

关键词： Speech recognition Mathematical model Speech Probabilistic logic Biological neural networks Speech processing

Threshold-Based Secure and Privacy-Preserving Message Verification in VANETs

学校读者我要写书评

暂无评论

Threshold-Based Secure and Privacy-Preserving Message Verifi...

IEEE International Conference on Trust, Security and Privacy in computing and Communications (TrustCom)

作者： Wei Gao Mingzhong Wang Liehuang Zhu Xiaoping Zhang Language Information Processing and Cloud Computing Application Beijing Institute of Technology National Key Lab of Vehicular Transmission China North Vehicle Research Institute

ISBN: (纸本)9781479965144

Messages spreading inside vehicular ad hoc networks (VANETs) generally need to achieve the property of verifiability and content integrity, while preserving user privacy. Otherwise, VANETs will either fall into chaos, or prevent users from embracing it. To achieve this goal, we propose a protocol, which contains a priori and posteriori countermeasures, to guarantee these features. The a priori process firstly verifies that each message is sent by a vehicle only once. Then it collects and checks whether the count of the message exceeds the threshold value to improve the trustworthiness of the message. The posteriori process verifies the integrity of the message, ensuring it is unchanged during transmission between the vehicle and the road side unit. The privacy is preserved by applying group signature. In case of disruptive events, the proposed solution can trace back to the source vehicle which generates the message.

关键词： Vehicles Privacy Authentication Protocols Public key Servers

Chasing Hypernyms in Vector Spaces with Entropy 14

学校读者我要写书评

暂无评论

Chasing Hypernyms in Vector Spaces with Entropy

14th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2014

作者： Santus, Enrico Lenci, Alessandro Lu, Qin im Walde, Sabine Schulte Dept. of Chinese and Bilingual Studies The Hong Kong Polytechnic University Hong Kong CoLing Lab Dept. of Philology Literature and Linguistics University of Pisa Italy Dept. of Computing The Hong Kong Polytechnic University Hong Kong Inst. for Natural Language Processing University of Stuttgart Germany

ISBN: (纸本)9781937284992

In this paper, we introduce SLQS, a new entropy-based measure for the unsupervised identification of hypernymy and its directionality in Distributional Semantic Models (DSMs). SLQS is assessed through two tasks: (i.) identifying the hypernym in hyponym-hypernym pairs, and (ii.) discriminating hypernymy among various semantic relations. In both tasks, SLQS outperforms other state-of-the-art measures. © 2014 Association for Computational Linguistics

关键词： Vector spaces

Earlier attention? Aspect-aware LSTM for aspect-based sentiment analysis

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Xing, Bowen Liao, Lejian Song, Dandan Wang, Jingang Zhang, Fuzhen Wang, Zhongyuan Huang, Heyan Lab of High Volume Language Information Processing & Cloud Computing Beijing Lab of Intelligent Information Technology School of Computer Science & Technology Beijing Institute of Technology Meituan-Dianping Group

Aspect-based sentiment analysis (ABSA) aims to predict fine-grained sentiments of comments with respect to given aspect terms or categories. In previous ABSA methods, the importance of aspect has been realized and verified. Most existing LSTM-based models take aspect into account via the attention mechanism, where the attention weights are calculated after the context is modeled in the form of contextual vectors. However, aspect-related information may be already discarded and aspect-irrelevant information may be retained in classic LSTM cells in the context modeling process, which can be improved to generate more effective context representations. This paper proposes a novel variant of LSTM, termed as aspect-aware LSTM (AA-LSTM), which incorporates aspect information into LSTM cells in the context modeling stage before the attention mechanism. Therefore, our AA-LSTM can dynamically produce aspect-aware contextual representations. We experiment with several representative LSTM-based models by replacing the classic LSTM cells with the AA-LSTM cells. Experimental results on SemEval-2014 Datasets demonstrate the effectiveness of AA-LSTM. Copyright © 2019, The Authors. All rights reserved.

关键词： Sentiment analysis

Multidirectional associative optimization of function-specificword representations

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Gerz, Daniela Vulic, Ivan Rei, Marek Reichart, Roi Korhonen, Anna Language Technology Lab University of Cambridge PolyAI Limited London United Kingdom Department of Computing Imperial College London Faculty of Industrial Engineering and Management Technion Iit

We present a neural framework for learning associations between interrelated groups of words such as the ones found in Subject-Verb-Object (SVO) structures. Our model induces a joint function-specific word vector space, where vectors of e.g. plausible SVO compositions lie close together. The model retains information about word group membership even in the joint space, and can thereby effectively be applied to a number of tasks reasoning over the SVO structure. We show the robustness and versatility of the proposed framework by reporting state-of-The-Art results on the tasks of estimating selectional preference and event similarity. The results indicate that the combinations of representations learned with our task-independent model outperform task-specific architectures from prior work, while reducing the number of parameters by up to 95%. Copyright © 2020, The Authors. All rights reserved.

关键词： Vector spaces

BAND: Biomedical Alert News Dataset

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Fu, Zihao Zhang, Meiru Meng, Zaiqiao Shen, Yannan Buckeridge, David Collier, Nigel Language Technology Lab University of Cambridge United Kingdom School of Computing Science University of Glasgow United Kingdom School of Population and Global Health McGill University Canada

Infectious disease outbreaks continue to pose a significant threat to human health and well-being. To improve disease surveillance and understanding of disease spread, several surveillance systems have been developed to monitor daily news alerts and social media. However, existing systems lack thorough epidemiological analysis in relation to corresponding alerts or news, largely due to the scarcity of well-annotated reports data. To address this gap, we introduce the Biomedical Alert News Dataset (BAND)1, which includes 1,508 samples from existing reported news articles, open emails, and alerts, as well as 30 epidemiology-related questions. These questions necessitate the model's expert reasoning abilities, thereby offering valuable insights into the outbreak of the disease. The BAND dataset brings new challenges to the NLP world, requiring better disguise capability of the content and the ability to infer important information. We provide several benchmark tasks, including Named Entity Recognition (NER), Question Answering (QA), and Event Extraction (EE), to show how existing models are capable of handling these tasks in the epidemiology domain. To the best of our knowledge, the BAND corpus is the largest corpus of well-annotated biomedical outbreak alert news with elaborately designed questions, making it a valuable resource for epidemiologists and NLP researchers alike. © 2023, CC BY.

关键词： Natural language processing systems

An Approach to Evaluation Index and Model of Undergraduates' Spoken English Pronunciation

学校读者我要写书评

暂无评论

An Approach to Evaluation Index and Model of Undergraduates'...

International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery

作者： Xin-guang Li Jia-hua Chen Zhen Chen Yingni Chen LAB of Language Engineering and Computing GDUFS Guangzhou China CISCO School of Informatics GDUFS Guangzhou China College of Continuing Education and Open College GDUFS Guangzhou China

ISBN: (纸本)9781509040940

To study and implement a computer evaluation system for spoken English pronunciation is important for learners to improve their spoken English. This paper introduces an undergraduate-oriented evaluation model of spoken English pronunciation and its related system, with four evaluation parameter of accuracy, speed, rhythm and intonation. This paper illustrates the necessity of each evaluation index, its computer realization method, and its weight in the overall evaluation model. Verified by experiments, the evaluation index and the model method adopted in this paper are reasonable and reliable.

关键词： Undergraduates Spoken English pronunciation Evaluation index Evaluation model

Learning sparse sentence encoding without supervision: An exploration of sparsity in variational autoencoders

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Prokhorov, Victor Li, Yingzhen Shareghi, Ehsan Collier, Nigel Language Technology Lab University of Cambridge United Kingdom Department of Data Science & AI Monash University Australia Department of Computing Imperial College London United Kingdom

It has been long known that sparsity is an effective inductive bias for learning efficient representation of data in vectors with fixed dimensionality, and it has been explored in many areas of representation learning. Of particular interest to this work is the investigation of the sparsity within the VAE framework which has been explored a lot in the image domain, but has been lacking even a basic level of exploration in NLP. Additionally, NLP is also lagging behind in terms of learning sparse representations of large units of text e.g., sentences. We use the VAEs that induce sparse latent representations of large units of text to address the aforementioned shortcomings. First, we move in this direction by measuring the success of unsupervised state-of-the-art (SOTA) and other strong VAE-based sparsification baselines for text and propose a hierarchical sparse VAE model to address the stability issue of SOTA. Then, we look at the implications of sparsity on text classification across 3 datasets, and highlight a link between performance of sparse latent representations on downstream tasks and its ability to encode task-related information. Copyright © 2020, The Authors. All rights reserved.

关键词： Natural language processing systems

Rewire-then-Probe: A Contrastive Recipe for Probing Biomedical Knowledge of Pre-trained language Models

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Meng, Zaiqiao Liu, Fangyu Shareghi, Ehsan Su, Yixuan Collins, Charlotte Collier, Nigel Language Technology Lab. University of Cambridge United Kingdom Department of Computing Science University of Glasgow United Kingdom Department of Data Science and AI Monash University Australia

Knowledge probing is crucial for understanding the knowledge transfer mechanism behind the pre-trained language models (PLMs). Despite the growing progress of probing knowledge for PLMs in the general domain, specialised areas such as biomedical domain are vastly under-explored. To facilitate this, we release a well-curated biomedical knowledge probing benchmark, MedLAMA, constructed based on the Unified Medical language System (UMLS) Metathesaurus. We test a wide spectrum of state-of-the-art PLMs and probing approaches on our benchmark, reaching at most 3% of acc@10. While highlighting various sources of domain-specific challenges that amount to this underwhelming performance, we illustrate that the underlying PLMs have a higher potential for probing tasks. To achieve this, we propose Contrastive-Probe, a novel self-supervised contrastive probing approach, that adjusts the underlying PLMs without using any probing data. While Contrastive-Probe pushes the acc@10 to 24%, the performance gap remains notable. Our human expert evaluation suggests that the probing performance of our Contrastive-Probe is underestimated as UMLS does not comprehensively cover all existing factual knowledge. We hope MedLAMA and Contrastive-Probe facilitate further developments of more suited probing techniques for this domain. Copyright © 2021, The Authors. All rights reserved.

关键词： Probes